Search Results

The device FusionSync contains automatic registration algorithms that are intended for the spatial synchronization of different series. The automatic algorithm is not intended for the registration of series from modalities other than: CT, conventional MRI, PET or SPECT. In addition, the product contains a manual mode (non-automatic) that allows the registration via user interaction such that for example automatic registration results can be refined. The intended clinical use is to display different 3D series from the same patient in spatial synchronization as for example, but not limited to, followup examinations. The displayed series can be visualized as MPR views with arbitrary 3D orientation. It is possible to overlay a registered series onto an MPR view. The spatial synchronization and optional overlay, based on the registration result, is intended to help the clinician to obtain a better understanding of the joint information of two registered images. The clinician retains the responsibility for making the diagnosis based on their standard procedures where the separate unregistered images are compared visually. FusionSync complements these clinical standard procedures.

FusionSync is a software program that provides a registration engine to align (register) pairs of images from same and different imaging modalities. The platform-independent registration engine is designed as a plug-in component that has the ability to extend the productivity of existing viewers like CAD workstations or PACS. The graphical user interface of FusionSync is designed as a plug-in component for avean workstation OsiriX PRO. It includes functionality to display the original volumetric data and the results of the registration operation. The graphical user interface allows to control the registration engine and fusion visualization.

Here's an analysis of the acceptance criteria and study information for the FusionSync device, based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

The provided document, a 510(k) summary, does not explicitly state quantitative acceptance criteria for FusionSync's performance. Instead, it relies on demonstrating substantial equivalence to a predicate device (Fusion7D) by comparing technological characteristics and features. The comparison focuses on functionality and speed rather than specific performance metrics like accuracy or precision with defined thresholds.

However, based on the "Technological Characteristics/Feature Comparison" table, we can infer some performance aspects:

Key takeaway: The submission argues that FusionSync's faster registration speed is a technological advancement, and the absence of features like landmark-based registration, live updates, or standalone software does not negatively impact effectiveness because they are either time-consuming, rarely used, or not diagnostically beneficial.

2. Sample Size Used for the Test Set and Data Provenance

The document does not mention any specific test set, its sample size, or data provenance (e.g., country of origin, retrospective/prospective) for a study to prove acceptance criteria.

The submission focuses entirely on non-clinical tests (software validation, verification, and testing per FDA guidance) to demonstrate substantial equivalence, rather than a clinical performance study.

3. Number of Experts Used to Establish Ground Truth for the Test Set and Qualifications

Since no clinical test set or study is described, there is no information provided regarding experts, their number, or qualifications for establishing ground truth.

4. Adjudication Method for the Test Set

As no test set or clinical study is described, no adjudication method is mentioned.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was done, Effect Size

No Multi-Reader Multi-Case (MRMC) comparative effectiveness study was conducted or reported in this 510(k) summary. The document explicitly states "DISCUSSION OF CLINICAL TESTS PERFORMED: N/A". Therefore, no effect size for human readers improving with AI vs. without AI assistance is provided.

6. If a Standalone (Algorithm Only Without Human-in-the-Loop Performance) was Done

The document states that "Performance testing included software validation, verification and testing per FDA's software validation guidance." This suggests that the algorithm's functionality and performance were tested in isolation as part of the software validation process. The "Automatic Registration" feature implies standalone algorithmic performance. However, no specific standalone performance study with reported metrics (e.g., accuracy against ground truth) is described. The comparison is feature-based against the predicate.

7. The Type of Ground Truth Used

Given that no clinical study is described, no specific type of ground truth (expert consensus, pathology, outcomes data, etc.) is mentioned as being used for performance evaluation of the device against clinical criteria. The "ground truth" implicitly referred to in software validation for a registration device would relate to the correctness of the spatial alignment based on mathematical or pre-defined transformations, rather than clinical diagnostic ground truth.

8. The Sample Size for the Training Set

The document does not provide any information regarding a training set sample size. This 510(k) pertains to a software device, and while it uses "automatic registration algorithms," it does not specify if these algorithms are machine learning-based requiring a distinct training phase. If they are based on traditional image processing and optimization techniques, a separate "training set" in the machine learning sense might not be applicable or explicitly mentioned.

9. How the Ground Truth for the Training Set Was Established

Since no training set is mentioned, no information on how its ground truth was established is provided.

Ask a specific question about this device